{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:35:39Z","timestamp":1782833739250,"version":"3.54.5"},"reference-count":157,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFB3900504"],"award-info":[{"award-number":["2021YFB3900504"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61725105"],"award-info":[{"award-number":["61725105"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171436"],"award-info":[{"award-number":["62171436"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tgrs.2022.3194732","type":"journal-article","created":{"date-parts":[[2022,7,28]],"date-time":"2022-07-28T19:34:31Z","timestamp":1659036871000},"page":"1-22","source":"Crossref","is-referenced-by-count":254,"title":["RingMo: A Remote Sensing Foundation Model With Masked Image Modeling"],"prefix":"10.1109","volume":"61","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0038-9816","authenticated-orcid":false,"given":"Xian","family":"Sun","sequence":"first","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peijin","family":"Wang","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4612-508X","authenticated-orcid":false,"given":"Wanxuan","family":"Lu","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3897-919X","authenticated-orcid":false,"given":"Zicong","family":"Zhu","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4294-6673","authenticated-orcid":false,"given":"Xiaonan","family":"Lu","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2158-559X","authenticated-orcid":false,"given":"Qibin","family":"He","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9428-9751","authenticated-orcid":false,"given":"Junxi","family":"Li","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7681-7020","authenticated-orcid":false,"given":"Xuee","family":"Rong","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6016-1787","authenticated-orcid":false,"given":"Zhujun","family":"Yang","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7082-2526","authenticated-orcid":false,"given":"Hao","family":"Chang","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qinglin","family":"He","sequence":"additional","affiliation":[{"name":"Ascend Computing Ecosystem Enablement Department, Huawei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guang","family":"Yang","sequence":"additional","affiliation":[{"name":"Ascend Computing Ecosystem Enablement Department, Huawei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1830-2595","authenticated-orcid":false,"given":"Ruiping","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing and the Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6121-5529","authenticated-orcid":false,"given":"Jiwen","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0450-6469","authenticated-orcid":false,"given":"Kun","family":"Fu","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref56","first-page":"10236","article-title":"Glow: Generative flow with invertible 1×1 convolutions","volume":"31","author":"kingma","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref58","first-page":"1","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"vincent","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref53","first-page":"4797","article-title":"Conditional image generation with PixelCNN decoders","volume":"29","author":"van den oord","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref52","first-page":"1747","article-title":"Pixel recurrent neural networks","author":"van oord","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref55","article-title":"Density estimation using real NVP","author":"dinh","year":"2016","journal-title":"arXiv 1605 08803"},{"key":"ref54","article-title":"NICE: Non-linear independent components estimation","author":"dinh","year":"2014","journal-title":"arXiv 1410 8516"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS46834.2022.9883441"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3390\/rs12111868"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00087"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3109345"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00129"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00646"},{"key":"ref44","first-page":"9640","article-title":"An empirical study of training self-supervised vision transformers","author":"chen","year":"2021","journal-title":"Proc IEEE\/CVF Int Conf Comput Vis (ICCV)"},{"key":"ref43","article-title":"Improved baselines with momentum contrastive learning","author":"chen","year":"2020","journal-title":"arXiv 2003 04297"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3069799"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3005403"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"691","DOI":"10.11834\/jrs.20211058","article-title":"Multi-satellite integrated processing and analysis method under remote sensing big data","volume":"25","author":"kun","year":"2021","journal-title":"National Remote Sensing"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3102629"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.12.004"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2982064"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2016.03.014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.11.023"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00350"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3070368"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2685945"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref37","first-page":"28","article-title":"iSAID: A large-scale dataset for instance segmentation in aerial images","author":"waqas zamir","year":"2019","journal-title":"Proc IEEE\/CVF Conf Comput Vis Pattern Recognit Workshops"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref31","article-title":"Masked autoencoders are scalable vision learners","author":"he","year":"2021","journal-title":"arXiv 2111 06377"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.03.005"},{"key":"ref30","article-title":"Self-supervised audiovisual representation learning for remote sensing data","author":"heidler","year":"2021","journal-title":"arXiv 2108 00688"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3056416"},{"key":"ref33","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.3390\/rs12101662"},{"key":"ref32","article-title":"SimMIM: A simple framework for masked image modeling","author":"xie","year":"2021","journal-title":"arXiv 2111 09886"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451652"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS47720.2021.9553741"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/rs12101662"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.05.001"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3066802"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.3390\/rs12101662"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3082630"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.2988032"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3037893"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.06.003"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3115569"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3090418"},{"key":"ref26","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01002"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3093557"},{"key":"ref22","article-title":"An empirical study of remote sensing pretraining","author":"wang","year":"2022","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS46834.2022.9883686"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3152250"},{"key":"ref28","article-title":"Self-supervised material and texture representation learning for remote sensing tasks","author":"akiva","year":"2021","journal-title":"arXiv 2112 01715"},{"key":"ref27","first-page":"22243","article-title":"Big self-supervised models are strong semi-supervised learners","volume":"33","author":"chen","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00928"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3174910"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3083113"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3113831"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00747"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3045474"},{"key":"ref129","article-title":"High-resolution representations for labeling pixels and regions","author":"sun","year":"2019","journal-title":"arXiv 1904 04514"},{"key":"ref97","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.12.015"},{"key":"ref99","article-title":"Oriented feature alignment for fine-grained object recognition in high-resolution satellite imagery","author":"ming","year":"2021","journal-title":"arXiv 2110 06628"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00926"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3062048"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00296"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00533"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3149394"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3093334"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.5194\/isprs-annals-V-2-2020-625-2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3021098"},{"key":"ref93","article-title":"Embedded self-distillation in compact multi-branch ensemble network for remote sensing scene classification","author":"zhao","year":"2021","journal-title":"arXiv 2104 00222"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01270"},{"key":"ref92","article-title":"MGML: Multigranularity multilevel feature ensemble network for remote sensing scene classification","author":"zhao","year":"2021","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2917952"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_11"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2974745"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref130","first-page":"550","article-title":"AlignSeg: Feature-aligned segmentation networks","volume":"44","author":"huang","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref91","article-title":"Deep feature aggregation framework driven by graph convolutional network for scene classification in remote sensing","author":"xu","year":"2021","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3092816"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3109061"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3093914"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00415"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3095166"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3097148"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3109661"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3065112"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3026221"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3121471"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2983560"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2994150"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2931801"},{"key":"ref145","year":"2020","journal-title":"MMSegmentation Openmmlab semantic segmentation toolbox and benchmark"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3114404"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2913861"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.3011405"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2018.06.005"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2979552"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2016.2616585"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2987060"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2920374"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2864987"},{"key":"ref109","article-title":"Deep adaptive proposal network for object detection in optical remote sensing images","author":"cheng","year":"2018","journal-title":"arXiv 1807 07327"},{"key":"ref106","article-title":"YOLOv3: An incremental improvement","author":"redmon","year":"2018","journal-title":"arXiv 1804 02767"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.3390\/rs10050734"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2867198"},{"key":"ref74","first-page":"1","article-title":"Recurrent transformer network for remote sensing scene categorisation","volume":"266","author":"chen","year":"2018","journal-title":"Proc BMVC"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.3390\/rs11050494"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2016.2601622"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2906883"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2778300"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3046756"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3093334"},{"key":"ref71","first-page":"3","article-title":"CBAM: Convolutional block attention module","author":"woo","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3015049"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2783902"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.2975541"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/8639367"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2845668"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"ref68","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref67","first-page":"30392","article-title":"Early convolutions help transformers see better","volume":"34","author":"xiao","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref117","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"Proc Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref69","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume":"32","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00388"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00418"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00350"},{"key":"ref63","article-title":"BEiT: BERT pre-training of image transformers","author":"bao","year":"2021","journal-title":"arXiv 2106 08254"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref113","article-title":"SCRDet++: Detecting small, cluttered and rotated objects via instance-level feature denoising and rotation loss smoothing","author":"yang","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref65","article-title":"LoveDA: A remote sensing land-cover dataset for domain adaptive semantic segmentation","author":"wang","year":"2021","journal-title":"arXiv 2110 08733"},{"key":"ref114","article-title":"MMDetection: Open MMLab detection toolbox and benchmark","author":"chen","year":"2019","journal-title":"ArXiv 1906 07155"},{"key":"ref60","first-page":"1691","article-title":"Generative pretraining from pixels","author":"chen","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"ref123","first-page":"801","article-title":"Encoder–decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref62","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv 2010 11929"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.549"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/36\/10006360\/09844015.pdf?arnumber=9844015","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,25]],"date-time":"2023-11-25T02:53:21Z","timestamp":1700880801000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9844015\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":157,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2022.3194732","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}